DEBM: Differential Evolution-Based Block Matching Algorithm

Abstract

Of all the motion estimation approaches, block matching approach is the most powerful and effective method for motion estimation of video sequences. In recent years nature-inspired algorithms are being used in an effective way for motion estimation. This study proposes a novel approach of motion estimation: differential evolution-based block matching algorithm for motion estimation. To showcase the effectiveness of the proposed work, we have used four well-known test video sequences. The video sequences used in the experiments have all the required characteristics like diverse resolutions, formats, and the frame count that are needed in input video sequences. The proposed approach is compared with standard block matching algorithms by considering the parameters like structural similarity (SSIM) and peak signal-to-noise ratio (PSNR). The empirical results indicate that our proposed algorithms perform better in comparison to standard block matching algorithms.